© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72264
    Prev
    Next
    INDEX
    Explanations

    state or condition described

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -1.35
     after
    -1.15
     which
    -1.09
    when
    -1.09
     to
    -1.03
    cznych
    -0.98
     людей
    -0.96
     through
    -0.96
     from
    -0.95
    ⭑
    -0.94
    POSITIVE LOGITS
     empleados
    1.23
     afbeeldingen
    1.23
     ajouté
    1.16
     vervangen
    1.12
     portavoz
    1.09
     rigueur
    1.09
    étape
    1.08
    を担当
    1.07
     víctima
    1.06
     onderdeel
    1.06
    Activations Density 0.080%

    No Known Activations